4.1: Rolling your own Web ML models from a blank canvas

Why it's on BrighterTube

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Introduces building web ML models from scratch without pre-built tools. Provides a roadmap for custom model development.

What you'll learn

A 3-minute video from Google for Developers: “4.1: Rolling your own Web ML models from a blank canvas”.

Programming & CS

Video by Google for Developers, played through YouTube's embedded player.

Part of Machine Learning for Web Developers (Web ML)

Google I/O 2012 - Go Concurrency Patterns Google for DevelopersProgramming & CS894K views

Google I/O 2009 - The Myth of the Genius Programmer Google for DevelopersProgramming & CS1.21M views

But what is a neural network? | Deep learning chapter 1 3Blue1BrownScience & Math25.1M views

The spelled-out intro to neural networks and backpropagation: building micrograd Andrej KarpathyProgramming & CS4.41M views

Transformers, the tech behind LLMs | Deep Learning Chapter 5 3Blue1BrownProgramming & CS11.6M views

Let's build GPT: from scratch, in code, spelled out.Andrej KarpathyProgramming & CS8.21M views

24:26

The Beauty of Bézier Curves Freya HolmérProgramming & CS2.23M views

Ruby Conf 12 - Y Not- Adventures in Functional Programming by Jim Weirich ConfreaksProgramming & CS65.7K views

“Hello, world” from scratch on a 6502 — Part 1 Ben EaterProgramming & CS5.85M views

2:27:41

CS50x 2024 - Lecture 1 - C CS50Programming & CS1.41M views

2:04:55

CS50x 2024 - Lecture 0 - Scratch CS50Programming & CS2.2M views

1:13:50

The Continuity of Splines Freya HolmérProgramming & CS1.89M views

Google I/O 2012 - Go Concurrency Patterns

Google for Developers894K views

Rob Pike demonstrates Go concurrency patterns — generators, fan-in, timeouts, quit channels and more — with runnable examples.

Google I/O 2009 - The Myth of the Genius Programmer

Google for Developers1.21M views

Google engineers on why the 'lone genius' myth hurts software teams, and how to collaborate, fail early and accept criticism.

But what is a neural network? | Deep learning chapter 1

3Blue1Brown25.1M views

Builds up what a neural network actually is — neurons as numbers, layers, weights and biases — using handwritten-digit recognition as the running example.

The spelled-out intro to neural networks and backpropagation: building micrograd

Andrej Karpathy4.41M views

Building micrograd, a tiny autograd engine, to understand backpropagation completely.

Transformers, the tech behind LLMs | Deep Learning Chapter 5

3Blue1Brown11.6M views

How transformer models (the 'T' in GPT) turn text into vectors and predict the next token, step by step.

Let's build GPT: from scratch, in code, spelled out.

Andrej Karpathy8.21M views

Building a GPT-style language model from scratch in code, following 'Attention Is All You Need'.

24:26

The Beauty of Bézier Curves

Freya Holmér2.23M views

Freya Holmér builds Bézier curves from linear interpolation up, covering de Casteljau's algorithm, derivatives, arc length and their use in games and graphics.

Ruby Conf 12 - Y Not- Adventures in Functional Programming by Jim Weirich

Confreaks65.7K views

Jim Weirich derives the Y combinator live, step by step, using nothing but Ruby lambdas, and along the way teaches the refactorings of lambda calculus.

“Hello, world” from scratch on a 6502 — Part 1

Ben Eater5.85M views

Building a computer around the 6502 processor on a breadboard and running 'Hello, world'.

2:27:41

CS50x 2024 - Lecture 1 - C

CS501.41M views

CS50x 2024 lecture 1: an introduction to C — syntax, types, conditionals, loops and compiling.

2:04:55

CS50x 2024 - Lecture 0 - Scratch

CS502.2M views

CS50x 2024 lecture 0: how computers represent information, algorithms, and first programs in Scratch.

1:13:50

The Continuity of Splines

Freya Holmér1.89M views

A follow-up on splines: the different kinds of continuity (C and G), and how Hermite, Catmull-Rom, B-splines and NURBS trade them off.